Towards Controllable Biases in Language Generation

Towards Controllable Biases in Language Generation

Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, and Nanyun Peng, in EMNLP-Finding, 2020.

Code

Download the full text

---

Abstract

We present a general approach towards controllable societal biases in natural language generation (NLG). Building upon the idea of adversarial triggers, we develop a method to induce societal biases in generated text when input prompts contain mentions of specific demographic groups. We then analyze two scenarios: 1) inducing negative biases for one demographic and positive biases for another demographic, and 2) equalizing biases between demographics. The former scenario enables us to detect the types of biases present in the model. Specifically, we show the effectiveness of our approach at facilitating bias analysis by finding topics that correspond to demographic inequalities in generated text and comparing the relative effectiveness of inducing biases for different demographics. The second scenario is useful for mitigating biases in downstream applications such as dialogue generation. In our experiments, the mitigation technique proves to be effective at equalizing the amount of biases across demographics while simultaneously generating less negatively biased text overall.

---

• Source Code

---

Bib Entry

@inproceedings{sheng2020towards,
  title = {Towards Controllable Biases in Language Generation},
  author = {Sheng, Emily and Chang, Kai-Wei and Natarajan, Premkumar and Peng, Nanyun},
  booktitle = {EMNLP-Finding},
  year = {2020}
}

---

Related Publications

1. A Meta-Evaluation of Measuring LLM Misgendering, COLM 2025, 2025
2. White Men Lead, Black Women Help? Benchmarking Language Agency Social Biases in LLMs, ACL, 2025
3. Controllable Generation via Locally Constrained Resampling, ICLR, 2025
4. On Localizing and Deleting Toxic Memories in Large Language Models, NAACL-Finding, 2025
5. Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification, EMNLP-Finding, 2024
6. Mitigating Bias for Question Answering Models by Tracking Bias Influence, NAACL, 2024
7. Are you talking to ['xem'] or ['x', 'em']? On Tokenization and Addressing Misgendering in LLMs with Pronoun Tokenization Parity, NAACL-Findings, 2024
8. Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems, EMNLP-Finding, 2023
9. Kelly is a Warm Person, Joseph is a Role Model: Gender Biases in LLM-Generated Reference Letters, EMNLP-Findings, 2023
10. The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks, ACL (short), 2023
11. Factoring the Matrix of Domination: A Critical Review and Reimagination of Intersectionality in AI Fairness, AIES, 2023
12. How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?, EMNLP (Short), 2022
13. On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations, ACL (short), 2022
14. Societal Biases in Language Generation: Progress and Challenges, ACL, 2021
15. "Nice Try, Kiddo": Investigating Ad Hominems in Dialogue Responses, NAACL, 2021
16. BOLD: Dataset and metrics for measuring biases in open-ended language generation, FAccT, 2021
17. The Woman Worked as a Babysitter: On Biases in Language Generation, EMNLP (short), 2019